© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16506
    Prev
    Next
    INDEX
    Explanations

    references to socioeconomic and industrialized terms in a document

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     joints
    -0.73
     sketches
    -0.71
     fir
    -0.68
     wheels
    -0.68
    alions
    -0.67
     whis
    -0.67
     sketch
    -0.66
     aliases
    -0.65
     encl
    -0.64
     knots
    -0.63
    POSITIVE LOGITS
     industrialized
    2.53
    orno
    0.95
    Ranked
    0.83
     Plains
    0.82
    Population
    0.80
    aceae
    0.79
    âĦ¢:
    0.78
    Indust
    0.77
    ð
    0.77
    ::::::::
    0.76
    Activations Density 0.008%

    No Known Activations